Data processing to remove outliers and inliers: A systematic literature study

Abstract

Outliers and inliers often arise during sample data acquisition. While outliers represent anomalous observations, inliers are erroneous data points within the main body of the dataset. It was aimed to conduct a systematic literature study (SLS) to survey methods and software employed for outlier and inlier removal, particularly within exploratory data analysis. The study was conducted in three phases: (i) systematic literature mapping (SLM), (ii) snowballing (SB), and (iii) SLR. Initially, 772 scientific studies were identified, subsequently narrowed down to 86 after applying selection criteria. Backward (BSB) and forward (FSB) snowballing further yielded 16 studies, resulting in a final pool of 102 studies for analysis. It was identified three outlier removal techniques (Chebyshev’s inequality, boxplot, and principal component analysis), one inlier removal technique (local Moran’s index), and thirteen commonly used software.